lrc tweaks

lyric_search_new/utils.py

@@ -88,10 +88,42 @@ class DataUtils:
     """
     Data Utils
     """
+
+    def __init__(self):
+        self.lrc_regex = regex.compile(r'\[([0-9]{2}:[0-9]{2})\.[0-9]{1,3}\](\s(.*)){0,}')
+
+
     def scrub_lyrics(self, lyrics: str) -> str:
         """Regex Chain"""
         lyrics = regex.sub(r'(\[.*?\])(\s){0,}(\:){0,1}', '', lyrics)
         lyrics = regex.sub(r'(\d?)(Embed\b)', '', lyrics, flags=regex.IGNORECASE)
         lyrics = regex.sub(r'\n{2}', '\n', lyrics)  # Gaps between verses
         lyrics = regex.sub(r'[0-9]\b$', '', lyrics)
-        return lyrics        
+        return lyrics   
+
+    def create_lrc_object(self, lrc_str: str) -> list[dict]:
+        lrc_out: list = []
+        for line in lrc_str.split("\n"):
+            _timetag = None
+            _words = None
+            if not line.strip():
+                continue
+            reg_helper = regex.findall(self.lrc_regex, line.strip())
+            if not reg_helper:
+                continue
+            reg_helper = reg_helper[0]
+            logging.debug("Reg helper: %s for line: %s; len: %s",
+                            reg_helper, line, len(reg_helper))
+            _timetag = reg_helper[0]
+            if not reg_helper[1].strip():
+                _words = "♪"
+            else:
+                _words = reg_helper[1]
+            lrc_out.append({
+                "timeTag": _timetag,
+                "words": _words,
+            })
+            logging.info("util: returning %s, type: %s",
+                         lrc_out, type(lrc_out))
+        return lrc_out        
+